© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 13503
    Prev
    Next
    INDEX
    Explanations

    terms related to leaving, exiting, or departure

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "exit," particularly in relation to political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elf
    -0.78
    illac
    -0.73
    sonian
    -0.73
    verbs
    -0.73
    MpServer
    -0.73
    acebook
    -0.71
    enegger
    -0.68
    rouse
    -0.68
    hed
    -0.66
    ened
    -0.64
    POSITIVE LOGITS
     exit
    0.86
     Exit
    0.83
    Exit
    0.77
    exit
    0.75
     exits
    0.73
     spoiler
    0.70
     door
    0.68
    door
    0.66
     Door
    0.66
     doors
    0.66
    Activations Density 0.012%

    No Known Activations